Sequential classification of customer behavior based on sequence-to-sequence learning with gated-attention neural networks
Sequential classification of customer behavior based on sequence-to-sequence learning with gated-attention neural networks
复制标题
DOI：
10.1007/s11634-022-00517-3
复制
发表时间：
2022-08
影响因子：
1.6
通讯作者：
Licheng Zhao;Yi Zuo;K. Yada
中科院分区：
文献类型：
--
作者：
Licheng Zhao;Yi Zuo;K. Yada
在过去的十年中，越来越多的超市开始使用RFID技术来跟踪消费者在店内的活动，以收集他们的购物行为数据。营销人员希望此类新型RFID数据能够提高现有客户细分的准确性，并从客户的角度提供有效的营销定位。因此，本文提出了将RFID数据与传统销售点（POS）数据相结合的综合工作，并提出了一种基于序列分类的模型来对消费者的购买行为进行分类和识别。我们选择了超市的一个岛区进行跟踪实验，收集了两个月的顾客行为数据。 RFID数据用于提取行为解释变量，例如停留时间和徘徊方向。对于这些客户，我们从POS系统中提取了他们过去三个月的购买历史数据，以定义客户背景和细分。最后，本文提出了一种基于序列到序列（Seq2seq）学习架构的新型分类模型。 Seq2seq 的编码器-解码器使用注意机制来追求顺序输入，编码器和解码器中的门控单元根据输入变量调整输出权重。实验结果表明，与其他基准模型相比，所提出的模型在客户分类和识别方面具有更高的准确性和曲线下面积值。此外，通过调整注意力机制，验证了异质客户之间行为描述变量的有效性。
During the last decade, an increasing number of supermarkets have begun to use RFID technology to track consumers' in-store movements to collect data on their shopping behavioral. Marketers hope that such new types of RFID data will improve the accuracy of the existing customer segmentation, and provide effective marketing positioning from the customer’s perspective. Therefore, this paper presents an integrated work on combining RFID data with traditional point of sales (POS) data, and proposes a sequential classification-based model to classify and identify consumers’ purchasing behavior. We chose an island area of the supermarket to perform the tracking experiment and collected customer behavioral data for two months. RFID data are used to extract behavior explanatory variables, such as residence time and wandering direction. For these customers, we extracted their purchasing historical data for the past three months from the POS system to define customer background and segmentation. Finally, this paper proposes a novel classification model based on sequence-to-sequence (Seq2seq) learning architecture. The encoder–decoder of Seq2seq uses an attention mechanism to pursue sequential inputs, with gating units in the encoder and decoder adjusting the output weights based on the input variables. The experimental results showed that the proposed model has a higher accuracy and area under curve value for customer classification and recognition compared with other benchmark models. Furthermore, the validity of behavioral description variables among heterogeneous customers was verified by adjusting the attention mechanism.